VerifyNet: Secure and Verifiable Federated Learning

Xu, Guowen; Li, Hongwei; Liu, Sen; Yang, Kan; Lin, Xiaodong

doi:10.1109/tifs.2019.2929409

Cited by 544 publications

(237 citation statements)

References 30 publications

Supporting

Mentioning

236

Contrasting

Order By: Relevance

“…VerifyNet tries to protect the users' privacy for the process of training and verify the reliability of the results that are sent back. The issue that the authors' highlight is that while there are several approaches focusing on security and privacy, there is still a problem of clients being able to verify if a server is functioning properly without compromising the users' privacy [98]. As such, the overall goal of this protocol is to address three major problems that federated training often runs into: 1) How to protect the users' privacy in workflow 2) Spoofing 3) How to offer offline support for users There are five rounds in the VerifyNet protocol that are: Initialization, Key Sharing, Masked Input, Unmasking, and Verification, with Fig.…”

Section: Figure 15 Fedcs Protocol Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

et al. 2020

View full text Add to dashboard Cite

This paper provides a comprehensive study of Federated Learning (FL) with an emphasis on enabling software and hardware platforms, protocols, real-life applications and use-cases. FL can be applicable to multiple domains but applying it to different industries has its own set of obstacles. FL is known as collaborative learning, where algorithm(s) get trained across multiple devices or servers with decentralized data samples without having to exchange the actual data. This approach is radically different from other more established techniques such as getting the data samples uploaded to servers or having data in some form of distributed infrastructure. FL on the other hand generates more robust models without sharing data, leading to privacy-preserved solutions with higher security and access privileges to data. This paper starts by providing an overview of FL. Then, it gives an overview of technical details that pertain to FL enabling technologies, protocols, and applications. Compared to other survey papers in the field, our objective is to provide a more thorough summary of the most relevant protocols, platforms, and real-life use-cases of FL to enable data scientists to build better privacy-preserving solutions for industries in critical need of FL. We also provide an overview of key challenges presented in the recent literature and provide a summary of related research work. Moreover, we explore both the challenges and advantages of FL and present detailed service use-cases to illustrate how different architectures and protocols that use FL can fit together to deliver desired results.

show abstract

Section: Figure 15 Fedcs Protocol Frameworkmentioning

confidence: 99%

“…The authors noted that VerifyNet was receptive to users dropping out of the FL learning process. VerifyNet was also able to achieve high security, but unfortunately, VerifyNet has high communication overheadm [98].…”

Section: Figure 15 Fedcs Protocol Frameworkmentioning

confidence: 99%

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

et al. 2020

View full text Add to dashboard Cite

show abstract

“…While this represents a large step-up in terms of addressing critical issues of data privacy and security, recent studies have shown that even in federated learning scenarios several risks can be found, particularly regarding reverse-engineering attacks that can extract sensitive information about the datasets directly from the model [96]. As such, it is imperative that future research addresses privacy-preserving constructs for AI, with some examples including multiparty computation schemes and differential privacy [97].…”

Section: Cybersecurity and Privacymentioning

confidence: 99%

Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook

et al. 2020

View full text Add to dashboard Cite

“…By exploiting a secure aggregation protocol and a secretsharing scheme, the privacy of each user-provided model can be guaranteed under an honest-but-curious and active adversarial setting [100], which supports an arbitrary subset of user dropouts. Other than the above schemes, to verify the correctness of the final aggregation result, a privacy-preserving and verifiable federated learning protocol has been designed with a homomorphic hash function and a secret sharing protocol [101]. However, secure multi-party computation may still leak sensitive information during the learning process.…”

Section: Privacy Preservationmentioning

confidence: 99%

FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing

Yin

Lin

Kong

et al. 2020

IEEE Open J. Signal Process.

181

View full text Add to dashboard Cite

In this overview paper, data-driven learning model-based cooperative localization and location data processing are considered, in line with the emerging machine learning and big data methods. We first review (1) state-of-the-art algorithms in the context of federated learning, (2) two widely used learning models, namely the deep neural network model and the Gaussian process model, and (3) various distributed model hyper-parameter optimization schemes. Then, we demonstrate various practical use cases that are summarized from a mixture of standard, newly published, and unpublished works, which cover a broad range of location services, including collaborative static localization/fingerprinting, indoor target tracking, outdoor navigation using low-sampling GPS, and spatio-temporal wireless traffic data modeling and prediction. Experimental results show that near centralized data fitting-and prediction performance can be achieved by a set of collaborative mobile users running distributed algorithms. All the surveyed use cases fall under our newly proposed Federated Localization (FedLoc) framework, which targets on collaboratively building accurate location services without sacrificing user privacy, in particular, sensitive information related to their geographical trajectories. Future research directions are also discussed at the end of this paper.

show abstract

VerifyNet: Secure and Verifiable Federated Learning

Cited by 544 publications

References 30 publications

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook

FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing

Contact Info

Product

Resources

About